Learning apparatus, identification apparatus, learning method, identification method, and computer program
A learning device includes: a data input unit configured to receive first data which is a learning target, second data for identifying the first data, and second past data that is used as data for identifying the first data during past learning and relates to learning content to be preserved; a combined data generation unit configured to generate combined data by combining the first data and the second data; and a parameter updating unit configured to update a parameter of a machine learning model based on features of the second past data and the combined data obtained by inputting the combined data and the second past data to the machine learning model.
1 . A learning device comprising:
a data inputter configured to receive first data which is a learning target, second data for identifying the first data, and second past data that is used as data for identifying the first data during past learning and relates to learning content to be preserved;
a combined data generator configured to generate combined data by combining the first data and the second data; and
a parameter updater configured to update a parameter of a machine learning model based on features of the second past data and the combined data obtained by inputting the combined data and the second past data to the machine learning model.
2 . The learning device according to claim 1 , wherein
the second data is one of data of a random noise pattern, data of a pattern in which a part of learning input data is changed, or data of a pattern represented by an average value of the learning input data.
3 . The learning device according to claim 1 , further comprising:
an identificator configured to identify the first data using features of the combined data and the second past data; and
a loss acquirer configured to acquire a loss using the first data, the second past data, and an identification result of the identificator.
4 . The learning device according to claim 3 , wherein
the loss acquirer acquires the loss based on regularization for restricting a range of a parameter updated by the parameter updater, a loss which is based on identification accuracy in the combined data, a loss which is based on identification accuracy in the first data, and a loss which is based on identification accuracy in the second data.
5 . A learning method comprising:
receiving first data which is a learning target, second data for identifying the first data, and second past data that is used as data for identifying the first data during past learning and relates to learning content to be preserved;
generating combined data by combining the first data and the second data; and
updating a parameter of a machine learning model based on features of the second past data and the combined data obtained by inputting the combined data and the second past data to the machine learning model.
6 . A non-transitory computer readable storage medium that stores a computer program to be executed by the computer;
receiving first data which is a learning target, second data for identifying the first data, and second past data that is used as data for identifying the first data during past learning and relates to learning content to be preserved;
generating combined data by combining the first data and the second data; and
updating a parameter of a machine learning model based on features of the second past data and the combined data obtained by inputting the combined data and the second past data to the machine learning model.